Repository navigation
Judge tuning (5/5): Add reference prices and usage docs - #136
Open
ErlisLushtaku wants to merge 38 commits into
Open
ErlisLushtaku wants to merge 38 commits into
ErlisLushtaku wants to merge 38 commits into
Conversation
This was referenced Oct 7, 2026
…judge-tuning-04-usage
…judge-tuning-04-usage
…judge-tuning-04-usage
…judge-tuning-04-usage
…judge-tuning-04-usage
…judge-tuning-04-usage
…erlislushtaku/feat/judge-tuning-04-usage
ErlisLushtaku
changed the title
ErlisLushtaku
changed the base branch from
erlislushtaku/feat/tune-judge
to
erlislushtaku/feat/judge-tuning-reference-prices
October 9, 2026 07:55
…judge-tuning-reference-prices # Conflicts: # judgearena/pricing.py # judgearena/tuning/runner.py # tests/test_tuning.py
…erlislushtaku/feat/judge-tuning-04-usage
ErlisLushtaku
changed the title
…judge-tuning-reference-prices
…erlislushtaku/feat/judge-tuning-04-usage
…judge-tuning-reference-prices
…erlislushtaku/feat/judge-tuning-04-usage
…judge-tuning-reference-prices # Conflicts: # tests/test_tuning.py
…erlislushtaku/feat/judge-tuning-04-usage
…judge-tuning-reference-prices # Conflicts: # tests/test_tuning.py
…erlislushtaku/feat/judge-tuning-04-usage
…erlislushtaku/feat/judge-tuning-04-usage
ErlisLushtaku
changed the title
ErlisLushtaku
changed the base branch from
erlislushtaku/feat/judge-tuning-reference-prices
to
erlislushtaku/feat/tune-judge
October 13, 2026 12:07
ErlisLushtaku
changed the title
ErlisLushtaku
marked this pull request as ready for review
October 13, 2026 12:51
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds automatic judge prices, the tuning example and the usage docs.
tune_judge.price_per_million_tokensgets its rate from the OpenRouter model catalog, for any backend. An override takes precedence and is either one rate or separate input/output rates. The rates are estimates for comparison, not what a provider charges.{store_root}/openrouter_pricing.json. It can be prefetched on the login node, since compute nodes have no internet. Resolved rates are frozen in the run'sprices.json, so resuming and helper workers don't fetch again and prices don't change mid-run.configs/tune_judge.yamlis an example with categorical and continuous parameters.Merge order: #138 → #135 → #140 → #133 → #136.